Conversational AI Designer

About TrueFan AI Enterprise

TrueFan AI is building the next generation of realtime avatar products for enterprise communication. We empower large scale organizations to create highly personalized, interactive video experiences. Our enterprise division works directly with top tier blue chip clients in India. In these highly regulated industries, accuracy, compliance, and brand safety are non-negotiable. We are looking for a highly skilled Conversational AI Designer to shape the intelligence and reliability of our realtime avatars.

Role Overview

You will be the core architect behind how our realtime avatars speak, reason, and interact with users. Your primary focus will be designing robust prompts, establishing strict safety guardrails, and implementing tool calling features to ensure our avatars provide completely accurate and compliant information across diverse enterprise use cases.

This is not a prompt-writing role in isolation. You will dive deep into real conversations, understand human nuance, and craft AI interactions that feel natural, emotionally intelligent, and outcome-driven. You're part linguist, part conversation designer, part prompt engineer, someone who instinctively understands what makes dialogue feel human while also grasping the underlying behavior of large language models.

Key Responsibilities

• Prompt Engineering & System Design

Craft, test, and optimize system prompts that drive the behavior of our realtime conversational avatars, ensuring tone consistency, reasoning accuracy, and compliance alignment with enterprise use cases.

• Safety & Guardrails Implementation

Build and enforce strict guardrails to prevent hallucinations, bias, and off-topic responses, ensuring full compliance with enterprise standards and regulatory requirements.

• Tool Calling & Data Integration

Design and manage tool calling workflows, enabling language models to securely query enterprise databases, APIs, and knowledge bases for factual information, with robust error handling and fallback strategies.

• Evaluation & Metrics Framework

Develop comprehensive evaluation frameworks to continuously measure prompt accuracy, intent recognition, conversational naturalness, compliance adherence, and business-outcome metrics (conversion rates, qualification accuracy, customer satisfaction).

• Conversation Flow Design & Optimization

Design scalable frameworks including prompt templates, tone/style guides, fallback strategies, and reusable conversation playbooks for multiple use cases across voice, video, and text modalities.

• Audit & Iterative Improvement

Audit chat logs and interaction data to identify failure points, understand user intent misalignments, and iteratively improve prompt logic with data-driven refinements.

• Stakeholder Collaboration

Collaborate closely with backend engineers, product managers, domain experts, compliance officers, and end-users to align AI behavior with specific enterprise use cases and regulatory requirements.

Required Qualifications

• Proven experience in prompt engineering, conversational design, or applied NLP within a production environment (1+ years minimum). Demonstrable prompt library or portfolio showcasing work with LLMs.
• Deep practical knowledge of large language models and their underlying mechanics, including fine-tuning, in-context learning, system prompt architecture, and model behavior across different contexts.
• Strong expertise in implementing tool calling, function calling, structured outputs, and integrations within prompt architectures (experience with ReAct patterns, agent frameworks, or LangChain preferred).
• Hands-on experience building safety guardrails and moderation layers for enterprise AI applications, including hallucination detection, prompt injection defense, and compliance validation logic.
• Ability to design and execute quantitative evaluation metrics for AI conversations (accuracy measurement, coherence scoring, intent recognition, compliance adherence metrics).
• Exceptional analytical skills and attention to detail with ability to identify subtle conversational failures and root cause analysis.
• Strong communication skills with ability to translate technical AI concepts to non-technical stakeholders and explain design decisions clearly.

Preferred Qualifications

• Prior experience building AI products for large-scale enterprises with understanding of compliance requirements, regulatory frameworks, and operational excellence in regulated environments.
• Familiarity with Python scripting for prompt testing, evaluation automation, and API integrations. Experience with LLM frameworks (LangChain, LangGraph, CrewAI, LlamaIndex).
• Experience with realtime voice or video AI products, multimodal conversational systems, or voice agent design.
• Background in conversation design, linguistics, psychology, communication, or related fields demonstrating understanding of dialogue theory and human-AI interaction psychology.
• Experience with evaluator prompts to assess accuracy, coherence, and conversational quality at scale.
• Knowledge of bias detection/mitigation in conversational systems.